Dealing with Unbalanced Classes in Machine Learning
In many real-world classification problems, we stumble upon training data with unbalanced classes. This means that the individual classes do not contain the same number of elements. For example, if we want to build an image-based skin cancer detection system [...]
Robot Localization II: The Histogram Filter
This is part 2 in a series of articles explaining methods for robot localization, i.e. determining and tracking a robot's location via noisy sensor measurements. You should start with the first part: Robot Localization I: Recursive Bayesian Estimation Idea The [...]
Robot Localization I: Recursive Bayesian Estimation
This is part 1 in a series of tutorials in which we explore methods for robot localization: the problem of tracking the location of a robot over time with noisy sensors and noisy motors, which is an important task for every [...]
Why the Chinese Room Argument is Flawed
This text deals with arguments against the possibility of so-called strong artificial intelligence, with a particular focus on the Chinese Room Argument devised by philosopher John Searle. We start with a description of the thesis that Searle wants to disprove. Then [...]
Gödel’s Incompleteness Theorem And Its Implications For Artificial Intelligence
Introduction This text gives an overview of Gödel’s Incompleteness Theorem and its implications for artificial intelligence. Specifically, we deal with the question whether Gödel’s Incompleteness Theorem shows that human intelligence could not be recreated by a traditional computer. Sections 2 [...]
Deep Learning From Scratch V: Multi-Layer Perceptrons
This is part 5 of a series of tutorials, in which we develop the mathematical and algorithmic underpinnings of deep neural networks from scratch and implement our own neural network library in Python, mimicing the TensorFlow API. Start with the first [...]